🚨 Excited to share our new work ✨ OneLife ✨, which investigates how an agent can infer executable symbolic world models 🌐 from a single unguided trajectory in a stochastic environment. I’m especially excited about our planning + evaluation contributions: 1️⃣ We support

🚨Introducing OneLife, a new framework to learn world dynamics as a executable probabilistic program, from a single, unguided episode in a stochastic, complex environment. ✨Highlights: ➡️ Inference only routes through relevant laws, solving scaling challenges in complex state

🚨 Excited to announce "One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration" --> (1) Our agent can infer/reverse engineer the laws of an unknown, stochastic environment from a single, unguided episode -- without requiring

Excited to be at #ICCV2025 in Hawaii!🌴 I'll present two papers: M3DocVQA/M3DocRAG (Mon) and CAPTURe (Tue). Check our poster sessions👇 and feel free to ping me to grab a coffee together I'm hiring PhD students to work on multimodal AI and robotics with me at JHU from Fall 2026!

🥳 Honored and grateful to be awarded an NDSEG Fellowship in Computer Science! 💫🇺🇸 Big thanks to my advisor Mohit Bansal for his guidance, and shoutout to my lab mates at UNC AI, collaborators, internship advisors, and mentors for their support 🤗 Excited to continue

🎉 Big congrats to Zaid on being awarded the NDSEG PhD Fellowship, for his innovative contributions in environment/data generation, skill-based self-improvement and adaptable agents, visual program synthesis, and world model inference! #ProudAdvisor 👇👇

Tough week! I also got impacted less than 3 months after joining. Ironically, I just landed some new RL infra features the day before. Life moves on. My past work spans RL, PEFT, Quantization, and Multimodal LLMs. If your team is working on these areas, I’d love to connect.

Yi Lin is a brilliant researcher with abundance of knowledge in different aspects of LLM/VLM training. Hire him!

🚨 🤯 Wow! Yi Lin is an amazing researcher, who works on very hard and important problems in LLM and VLM training, RL, PEFT, Quantization, etc. -- ironically, he had several other top offers just a few months ago! Hire him ASAP if you want to pick up a top talent (and several

🥳🥳 Honored and grateful to be awarded a 2025 Google PhD Fellowship in Machine Learning and ML Foundations for my research on machine unlearning, defenses against adversarial attacks, and multi-agent privacy! ✨ Deep gratitude to my advisor Mohit Bansal for his constant

This is so cool! Adding images or audio makes the model easier to be persuaded. Nice work with a large-scale dataset + systematic analysis 🙌

It was an honor and pleasure to give a keynote at the 28th European Conference on Artificial Intelligence (#ECAI2025) in beautiful Bologna, and engage in enthusiastic discussions about trustworthy + calibrated agents, collaborative reasoning + privacy, and controllable multimodal

🎉 Excited to share that 5/5 of my papers (3 main, 2 findings) have been accepted at #EMNLP2025, in video/multimodal reasoning, instructional video editing, and efficient LLM adaptation & reasoning! 🚨 I’m recruiting Ph.D. students to join the Multimodal AI Group at NTU College

🚨 Excited to announce Gistify!, where a coding agent must extract the gist of a repository: generate a single, executable, and self-contained file that faithfully reproduces the behavior of a given command (e.g., a test or entrypoint). ✅ It is a lightweight, broadly applicable

🚨 Check out our awesome students/postdocs' papers at #EMNLP2025 and say hi to them 👋! Also, I will give a keynote (virtually) on "Attributable, Conflict-Robust, and Multimodal Summarization with Multi-Source Retrieval" at the NewSumm workshop. -- Jaehong (in-person) finished

(detailed links/websites + summary 🧵's of these papers attached below FYI 👇) -- MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning Justin Chih-Yao Chen Archiki Prasad Swarnadeep Saha Elias Stengel-Eskin arxiv.org/abs/2409.12147 x.com/cyjustinchen/s…

I'll be presenting ✨MAgICoRe✨ virtually tonight at 7 PM ET / 8 AM CST (Gather Session 3)! I'll discuss 3 key challenges in LLM refinement for reasoning, and how MAgICoRe tackles them jointly: 1⃣ Over-correction on easy problems 2⃣ Failure to localize & fix its own errors 3⃣

So excited to share this work (which received very high reviewer scores!) led by Sapir! Why wait for a full sentence to find a hallucination? We built a model that detects factual errors on prefixes as they’re generated. This leads to huge faithfulness gains (our 3B model

🎉Congrats to Vaidehi (advised by Mohit Bansal) for being awarded the prestigious Google PhD Fellowship, recognizing “researchers who understand that accelerating scientific discovery is vital to solving the world’s toughest challenges,” for her research on unlearning and privacy!

🎉 Excited to share that our 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗖𝘂𝗹𝘁𝘂𝗿𝗮𝗹 𝗦𝗮𝗳𝗲𝘁𝘆 paper is accepted at TMLR 2025! Grateful to all collaborators — this continues our series of projects on 𝗰𝘂𝗹𝘁𝘂𝗿𝗮𝗹 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗶𝘁𝘆 𝗮𝗻𝗱 𝘀𝗮𝗳𝗲𝘁𝘆: 1️⃣ SafeWorld: Geo-Diverse Safety